Object Detection to Identify and Track Objects | Fritz AI

Object Detection

SNAPML MOBILE
Use Object Detection to identify and track things within the contents of an image or each frame of live video. Enhances a range of experiences from photography to autonomy.
 

Custom Image Segmentation

Quickly move from an idea to a production-ready Image Segmentation model with Fritz AI.

Pre-Trained Object Detection Models

Add Object Detection features to iOS and Android apps with pre-trained models and only a few lines of code.

Mobile Object Detection

Objects Detected

  • Airplane
  • Apple
  • Backpack
  • Banana
  • Baseball Bat
  • Baseball Glove
  • Bear
  • Bed
  • Bench
  • Bicycle
  • Bird
  • Boat
  • Book
  • Bottle
  • Bowl
  • Broccoli
  • Bus
  • Cake
  • Car
  • Carrot
  • Cat
  • Cell Phone
  • Chair
  • Clock
  • Couch
  • Cow
  • Cup
  • Dining Table
  • Dog
  • Donut
  • Elephant
  • Fire Hydrant
  • Fork
  • Frisbee
  • Giraffe
  • Hair Drier
  • Handbag
  • Horse
  • Hot Dog
  • Keyboard
  • Kite
  • Knife
  • Laptop
  • Microwave
  • Motorcycle
  • Mouse
  • Orange
  • Oven
  • Parking Meter
  • Person
  • Pizza
  • Potted Plant
  • Refrigerator
  • Remote
  • Sandwich
  • Scissors
  • Sheep
  • Sink
  • Skateboard
  • Skis
  • Snowboard
  • Spoon
  • Sports Ball
  • Stop Sign
  • Suitcase
  • Surfboard
  • Teddy Bear
  • Tennis Racket
  • Tie
  • Toaster
  • Toilet
  • Toothbrush
  • Traffic Light
  • Train
  • Truck
  • Tv
  • Umbrella
  • Vase
  • Wine Glass
  • Zebra

Getting Started

import Fritz

var objectModel: FritzVisionObjectModelFast?

let image = FritzVisionImage(buffer: sampleBuffer)

guard let results = try? objectModel.predict(image) else { return }
Object Detection

The Swift code sample here illustrates how simple it can be to use object detection in your app. Use the links below to access additional documentation, code samples, and tutorials that will help you get started.

Features

Recognizes Objects

Bounding boxes provided for each object detected.

Our pre-trained models are trained on COCO, a large-scale object detection dataset.

Model Variants

Fast: Optimized for speed, best for processing video streams in real-time or on older devices.

Accurate: Optimized for higher accuracy where prediction quality is more important than speed.

Small: Optimized for size, keep your application bundle size low and conserve bandwidth.

Runs On-Device

All predictions / model inferences are made completely on-device.

No internet connection is required to interpret images or video.

No internet dependency means super-fast performance.

Cross-Platform SDKs

Supported mobile platforms:

  • Android Object Detection
  • iOS Object Detection
Live Video Performance

Runs on live video with a fast frame rate.

Exact FPS performance varies depending on device, but it is possible to run this feature on live video on modern mobile devices.

Technical Specifications

Architecture

SSDLite + MobileNet V2 variant

Model Size

~17 MB

FLOPS

800 M

Input

300x300-pixel image

Output

Offsets for >2,000 candidate bounding boxes

Class labels for each box

Confidence scores for each box

Formats

Core ML, TensorFlow, TensorFlow Lite, TensorFlow Mobile, Keras

Benchmarks

18 FPS on iPhone X

8 FPS on Pixel 2